Artificial intelligence to evaluate chest CT scans for COVID-19


The Shanghai Public Health Clinical Centre (SPHCC), together with Yitu Healthcare, an AI start-up based in Shanghai, have developed an intelligent chest CT assessment system for COVID-19.

The system, using AI algorithms, classifies the severity of various lung diseases that cause local, diffuse lesions and involve the entire lung.

The system accurately measures the level of the disease through quantitative and omic analysis of key features of the image, such as morphology, gamma and density of the lesion. The system can also provide dynamic 4D contrast of lung lesions, helping in judging the clinical condition, evaluating treatment effectiveness and predicting prognosis.

The severity classification of COVID-19 is the focus of clinical attention. The method of quantitative assessment of lesions involves multiple factors such as cumulative lung volume range and lesion density, and there is currently no uniform standard.

In the past, quantitative assessment was carried out by hand through Regions of Interest (ROI), which usually took several hours. Efficiency was low and clinical promotion was difficult. Using this new AI-based system, the detection of the lesion area can be performed automatically, and the quantitative analysis can be completed in 2-3 seconds. This greatly improves the efficiency of an accurate quantitative analysis.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s